Infant behavior state detection method based on target detection

The invention discloses an infant behavior state detection method based on target detection. According to the invention, the monitoring process mainly comprises the following steps: firstly, performing function selection on whether an infant sleeps or not so as to determine a specific monitoring tas...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HUANG HAO, ZHU ZEDE, WANG QISHENG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator HUANG HAO
ZHU ZEDE
WANG QISHENG
description The invention discloses an infant behavior state detection method based on target detection. According to the invention, the monitoring process mainly comprises the following steps: firstly, performing function selection on whether an infant sleeps or not so as to determine a specific monitoring task, and if the infant selects to sleep, selecting a judgment basis for kicking a quilt; the obtained RGB video frame is preprocessed; then, inputting the preprocessed picture into a YOLOX-tiny target detection algorithm based on structure simplification and feature enhancement improvement, so as to obtain an infant positioning and behavior state classification preliminary result; then, data storage is carried out, and detection data is processed and analyzed based on a mode filter thought; and finally, outputting infant behavior state detection results under different function selection conditions, and giving an alarm in time when the infant climbs, kicks a quilt and is lost. The method is of great significance in r
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116612422A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116612422A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116612422A3</originalsourceid><addsrcrecordid>eNrjZHDwzEtLzCtRSErNSCzLzC9SKC5JLElVSEktSU0uyczPU8hNLcnIT1FISixOTVEA8ksSi9JTSxAKeBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGZmaGRiZGRozExagDPVzFM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Infant behavior state detection method based on target detection</title><source>esp@cenet</source><creator>HUANG HAO ; ZHU ZEDE ; WANG QISHENG</creator><creatorcontrib>HUANG HAO ; ZHU ZEDE ; WANG QISHENG</creatorcontrib><description>The invention discloses an infant behavior state detection method based on target detection. According to the invention, the monitoring process mainly comprises the following steps: firstly, performing function selection on whether an infant sleeps or not so as to determine a specific monitoring task, and if the infant selects to sleep, selecting a judgment basis for kicking a quilt; the obtained RGB video frame is preprocessed; then, inputting the preprocessed picture into a YOLOX-tiny target detection algorithm based on structure simplification and feature enhancement improvement, so as to obtain an infant positioning and behavior state classification preliminary result; then, data storage is carried out, and detection data is processed and analyzed based on a mode filter thought; and finally, outputting infant behavior state detection results under different function selection conditions, and giving an alarm in time when the infant climbs, kicks a quilt and is lost. The method is of great significance in r</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230818&amp;DB=EPODOC&amp;CC=CN&amp;NR=116612422A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230818&amp;DB=EPODOC&amp;CC=CN&amp;NR=116612422A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HUANG HAO</creatorcontrib><creatorcontrib>ZHU ZEDE</creatorcontrib><creatorcontrib>WANG QISHENG</creatorcontrib><title>Infant behavior state detection method based on target detection</title><description>The invention discloses an infant behavior state detection method based on target detection. According to the invention, the monitoring process mainly comprises the following steps: firstly, performing function selection on whether an infant sleeps or not so as to determine a specific monitoring task, and if the infant selects to sleep, selecting a judgment basis for kicking a quilt; the obtained RGB video frame is preprocessed; then, inputting the preprocessed picture into a YOLOX-tiny target detection algorithm based on structure simplification and feature enhancement improvement, so as to obtain an infant positioning and behavior state classification preliminary result; then, data storage is carried out, and detection data is processed and analyzed based on a mode filter thought; and finally, outputting infant behavior state detection results under different function selection conditions, and giving an alarm in time when the infant climbs, kicks a quilt and is lost. The method is of great significance in r</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDwzEtLzCtRSErNSCzLzC9SKC5JLElVSEktSU0uyczPU8hNLcnIT1FISixOTVEA8ksSi9JTSxAKeBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGZmaGRiZGRozExagDPVzFM</recordid><startdate>20230818</startdate><enddate>20230818</enddate><creator>HUANG HAO</creator><creator>ZHU ZEDE</creator><creator>WANG QISHENG</creator><scope>EVB</scope></search><sort><creationdate>20230818</creationdate><title>Infant behavior state detection method based on target detection</title><author>HUANG HAO ; ZHU ZEDE ; WANG QISHENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116612422A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HUANG HAO</creatorcontrib><creatorcontrib>ZHU ZEDE</creatorcontrib><creatorcontrib>WANG QISHENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HUANG HAO</au><au>ZHU ZEDE</au><au>WANG QISHENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Infant behavior state detection method based on target detection</title><date>2023-08-18</date><risdate>2023</risdate><abstract>The invention discloses an infant behavior state detection method based on target detection. According to the invention, the monitoring process mainly comprises the following steps: firstly, performing function selection on whether an infant sleeps or not so as to determine a specific monitoring task, and if the infant selects to sleep, selecting a judgment basis for kicking a quilt; the obtained RGB video frame is preprocessed; then, inputting the preprocessed picture into a YOLOX-tiny target detection algorithm based on structure simplification and feature enhancement improvement, so as to obtain an infant positioning and behavior state classification preliminary result; then, data storage is carried out, and detection data is processed and analyzed based on a mode filter thought; and finally, outputting infant behavior state detection results under different function selection conditions, and giving an alarm in time when the infant climbs, kicks a quilt and is lost. The method is of great significance in r</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116612422A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Infant behavior state detection method based on target detection
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T06%3A21%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=HUANG%20HAO&rft.date=2023-08-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116612422A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true